Set up with an AI agent
A ready-to-copy prompt so Claude Code, Cursor or Codex can read the DataxLand docs and connect MCP for you.
The DataxLand docs have a Markdown version for AI agents. Paste the prompt below into the coding agent on your machine:
Read https://dataxland.com/en/docs/mcp.md and https://dataxland.com/llms.txt.
Help me add an MCP server named "dataxland" to your MCP configuration with the token I will paste,
then call the tool that lists metrics to check the connection. Do not save the token to any file in the repo.Resources for agents
| Path | Contents |
|---|---|
| /llms.txt | Index of the docs and main pages, following the llms.txt convention |
| /llms-full.txt | The full docs as Markdown |
/en/docs/<page>.md | The Markdown version of each docs page |
Notes
- An MCP token is a secret: paste it into your client's configuration, never into a public chat or a commit.
- The agent can only read approved metrics; it cannot read raw tables.
MCP server
Connect Claude Desktop, Claude Code, Cursor or your own AI agent to a workspace's approved metrics over the Model Context Protocol — tokens, scopes, client config and tools.
HTTP API overview
Conventions of the DataxLand HTTP API — Bearer authentication, choosing a workspace, the error shape, rate limits (429, Retry-After), quotas (402) and resource groups.